rm(list=ls())
Version info: R 3.2.3, Biobase 2.30.0, GEOquery 2.40.0, limma 3.26.8
R scripts generated Sun Aug 11 23:08:50 EDT 2019
################################################################
rm(list=ls())
# 使用limma包对数据分析
library(Biobase)
library(GEOquery)
library(limma)
# 从GEO加载series与platform数据
gset <- getGEO("GSE101728", GSEMatrix =TRUE, AnnotGPL=FALSE)##series
if (length(gset) > 1) idx <- grep("GPL21047", attr(gset, "names")) else idx <- 1##platform
gset <- gset[[idx]]##由于该整个数据是一个list，一个元素，所以需要取该数据的第一个list的第一个元素
# 从下载的平台获取ID名字
fvarLabels(gset) <- make.names(fvarLabels(gset))
# group names for all samples
gsms <- "1010101XX0XXXX"
sml <- c()
for (i in 1:nchar(gsms)) { sml[i] <- substr(gsms,i,i) }
# eliminate samples marked as "X"
sel <- which(sml != "X")
sml <- sml[sel]
gset <- gset[ ,sel]
# log2 transform
ex <- exprs(gset)
qx <- as.numeric(quantile(ex, c(0., 0.25, 0.5, 0.75, 0.99, 1.0), na.rm=T))
LogC <- (qx[5] > 100) ||
(qx[6]-qx[1] > 50 && qx[2] > 0) ||
(qx[2] > 0 && qx[2] < 1 && qx[4] > 1 && qx[4] < 2)
if (LogC) { ex[which(ex <= 0)] <- NaN
exprs(gset) <- log2(ex) }
# set up the data and proceed with analysis
sml <- paste("G", sml, sep="") # set group names
fl <- as.factor(sml)
gset$description <- fl
design <- model.matrix(~ description + 0, gset)
colnames(design) <- levels(fl)
fit <- lmFit(gset, design)
cont.matrix <- makeContrasts(G1-G0, levels=design)
fit2 <- contrasts.fit(fit, cont.matrix)
fit2 <- eBayes(fit2, 0.01)
tT <- topTable(fit2, adjust="fdr", sort.by="B", number=250)
##这里需要注意的是只选取了前250个数据
tT <- subset(tT, select=c("ID","adj.P.Val","P.Value","t","B","logFC","RANGE_START",
"RANGE_END","RANGE_STRAND","SEQUENCE","GB_ACC","ORF","SPOT_ID"))
write.table(tT, file=stdout(), row.names=F, sep="\t")
################################################################
# Boxplot for selected GEO samples
library(Biobase)
library(GEOquery)
# load series and platform data from GEO
gset <- getGEO("GSE101728", GSEMatrix =TRUE, getGPL=FALSE)
if (length(gset) > 1) idx <- grep("GPL21047", attr(gset, "names")) else idx <- 1
gset <- gset[[idx]]
# group names for all samples in a series
gsms <- "1010101XX0XXXX"
sml <- c()
for (i in 1:nchar(gsms)) { sml[i] <- substr(gsms,i,i) }
sml <- paste("G", sml, sep="") #set group names
# eliminate samples marked as "X"
sel <- which(sml != "X")
sml <- sml[sel]
gset <- gset[ ,sel]
# order samples by group
ex <- exprs(gset)[ , order(sml)]
sml <- sml[order(sml)]
fl <- as.factor(sml)
labels <- c("cancer+tissue","adjacent+tissue")
# set parameters and draw the plot
palette(c("#dfeaf4","#f4dfdf", "#AABBCC"))
dev.new(width=4+dim(gset)[[2]]/5, height=6)
par(mar=c(2+round(max(nchar(sampleNames(gset)))/2),4,2,1))
title <- paste ("GSE101728", '/', annotation(gset), " selected samples", sep ='')
boxplot(ex, boxwex=0.6, notch=T, main=title, outline=FALSE, las=2, col=fl)
legend("topleft", labels, fill=palette(), bty="n")
write.table(tT,file = '下载处理数据.RData')